npx skills add https://github.com/jaganpro/sf-skills --skill sf-flow当用户需要进行 Flow 设计或 Flow XML 工作 时使用此技能:记录触发流、屏幕流、自动启动流、计划流或平台事件流,包括验证、架构选择和安全部署顺序。
当工作涉及以下内容时,使用 sf-flow:
.flow-meta.xml 文件当用户进行以下操作时,请委托给其他技能:
询问或推断:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
在构建之前,确认 Flow 是正确的解决方案,而不是:
| 需求 | 默认流类型 |
|---|---|
| 保存前更新同一记录 | before-save 记录触发流 |
| 相关记录操作 / 邮件 / 调用外部服务 | after-save 记录触发流 |
| 引导式用户界面 | 屏幕流 |
| 可重用的后台逻辑 | 自动启动流 / 子流 |
| 计划处理 | 计划流 |
| 事件驱动的声明式响应 | 平台事件流 |
| AI 评估路由(情绪、意图、语气) | 带有 AI 决策元素的自动启动流 |
优先使用提供的资源:
assets/record-triggered-before-save.xmlassets/record-triggered-after-save.xmlassets/screen-flow-template.xmlassets/autolaunched-flow-template.xmlassets/scheduled-flow-template.xmlassets/platform-event-flow-template.xmlassets/ai-decision-template.xmlassets/subflows/重点关注:
使用:
$Record完成时,按此顺序报告:
建议格式:
Flow: <名称>
Type: <流类型>
Files: <路径>
Design: <触发选择、子流、关键决策>
Risks: <批量安全性、故障路径、依赖项>
Next step: <试运行部署、激活或测试>
| 需求 | 委托给 | 原因 |
|---|---|---|
| 首先创建对象/字段 | sf-metadata | 架构就绪 |
| 部署/激活流 | sf-deploy | 安全部署顺序 |
| 创建真实的批量测试数据 | sf-data | 部署后验证 |
| 创建 Apex 操作 / 可调用方法 | sf-apex | 命令式逻辑 |
| 在屏幕流中嵌入 LWC | sf-lwc | 自定义 UI 组件 |
| 向 Agentforce 公开 Flow | sf-ai-agentscript | 座席操作编排 |
| 分数 | 含义 |
|---|---|
| 88+ | 可用于生产的 Flow |
| 75–87 | 良好的 Flow,但有一些待审查项 |
| 60–74 | 功能正常,但需要更强的护栏 |
| < 60 | 不安全 / 不完整,不适合部署 |
每周安装数
293
代码库
GitHub 星标
223
首次出现
Jan 22, 2026
安全审计
安装于
codex281
cursor280
gemini-cli278
opencode278
github-copilot276
amp272
Use this skill when the user needs Flow design or Flow XML work : record-triggered, screen, autolaunched, scheduled, or platform-event Flows, including validation, architecture choices, and safe deployment sequencing.
Use sf-flow when the work involves:
.flow-meta.xml filesDelegate elsewhere when the user is:
Ask for or infer:
Before building, confirm Flow is the right answer rather than:
| Need | Default flow type |
|---|---|
| same-record update before save | before-save record-triggered |
| related-record work / emails / callouts | after-save record-triggered |
| guided UI | screen flow |
| reusable background logic | autolaunched / subflow |
| scheduled processing | scheduled flow |
| event-driven declarative response | platform-event flow |
| AI-evaluated routing (sentiment, intent, tone) | autolaunched with AI Decision element |
Prefer the provided assets:
assets/record-triggered-before-save.xmlassets/record-triggered-after-save.xmlassets/screen-flow-template.xmlassets/autolaunched-flow-template.xmlassets/scheduled-flow-template.xmlassets/platform-event-flow-template.xmlassets/ai-decision-template.xmlassets/subflows/Focus on:
Use:
$RecordWhen finishing, report in this order:
Suggested shape:
Flow: <name>
Type: <flow type>
Files: <paths>
Design: <trigger choice, subflows, key decisions>
Risks: <bulk safety, fault paths, dependencies>
Next step: <dry-run deploy, activate, or test>
| Need | Delegate to | Reason |
|---|---|---|
| create objects / fields first | sf-metadata | schema readiness |
| deploy / activate flow | sf-deploy | safe deployment sequence |
| create realistic bulk test data | sf-data | post-deploy verification |
| create Apex actions / invocables | sf-apex | imperative logic |
| embed LWC in a screen flow | sf-lwc | custom UI components |
| expose Flow to Agentforce | sf-ai-agentscript |
| Score | Meaning |
|---|---|
| 88+ | production-ready Flow |
| 75–87 | good Flow with some review items |
| 60–74 | functional but needs stronger guardrails |
| < 60 | unsafe / incomplete for deployment |
Weekly Installs
293
Repository
GitHub Stars
223
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
codex281
cursor280
gemini-cli278
opencode278
github-copilot276
amp272
agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试
140,500 周安装
| agent action orchestration |